Abstract

This paper presents some case study frameworks to limelight SVM classifiers as most efficient one compared to existing classifiers like Otsu, k-means and fuzzy c-means. In general, Computed Tomography (CT) and Magnetic Resonance Imaging (MR) are more dominant imaging technique for any brain lesions detection like brain tumor, Alzheimer' disease and so on. MR imaging takes a lead technically for imaging medical images due to its possession of large spatial resolution and provides better contrast for the soft tissues like white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). The usual method used for classification of lesions in brain images consists of pre-processing, feature extraction, feature reduction and classification. Early detection of the tumor region without much time lapse in computation can be achieved by using efficient SVM classifier model. Brain tumor grade classifications with the assistance of morphologically selected features are extracted and tumor classification is attained using SVM classifier. The assessment of SVM classifications are evaluated through metrics termed as sensitivity, exactness and accuracy of segmentation. These measures are then compared with existing methods to exhibit the SVM classifier as significant classifier model. Dr. R Manjunatha Prasad | Roopa B S"SVM Classifiers at it Bests in Brain Tumor Detection using MR Images" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-5 , August 2018, URL: http://www.ijtsrd.com/papers/ijtsrd18372.pdf http://www.ijtsrd.com/engineering/electronics-and-communication-engineering/18372/svm-classifiers-at-it-bests-in-brain-tumor-detection-using-mr-images/dr-r-manjunatha-prasad

Authors and Affiliations